基于相邻像素差异值的车牌定位算法  

License plate location algorithm based on adjacent pixels difference

作　　者：韦玉科[1] 欧阳发 WEI Yu-ke;OUYANG Fa(College of Computer, Guangdong University of Technology, Guangzhou 510006, China)

机构地区：[1]广东工业大学计算机学院,广东广州510006

出　　处：《计算机工程与设计》2018年第5期1387-1392,1404,共7页Computer Engineering and Design

基　　金：广东省科技计划基金项目(2014A040402007)

摘　　要：为解决交通车辆管理中的车牌定位问题,提出一种基于相邻像素差异值的车牌定位算法。在预处理阶段利用圆弧函数进行处理,提出相邻像素差异值算法提取车牌字符边缘;进行边缘检测、分块处理、高边缘块重组等筛选出候选区域;在候选确认阶段提出R+G通道灰度化方法与自适应均值二值化方法进行候选区域二值处理,结合车牌字符分布特征进行过滤伪候选区并获取车牌区域。实验结果表明,该算法的定位准确度较高,为97.5%,算法运行时间低至0.62s,具有一定实用价值。To solve the license plate location problem in the management of vehicle,a license plate location algorithm based on the difference value of adjacent pixels was proposed.In the stage of pretreatment,arc function was used to enhance the difference of adjacent pixels.The algorithm of difference value of adjacent pixels was proposed to detect the pixel of license plate character edge.The edge detection,block restructuring were used to screen out these candidates.In the stage of candidate verification,R＋G channels graying algorithm and adaptive average-value were proposed to get binarization of these candidates,and the distribution information of license plate character was used to pick the right candidate and get the location of license plate.Experimental results show that the proposed algorithm achieves ideal results with correct rate of 97.5% and the average run time of 0.62 s.

关 键 词：车牌定位 圆弧函数 相邻像素差异值 R+G通道 自适应均值 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]